Can a local model replace Jev as a prompt-injection gate? A 718-item benchmark
Testing 718 items on Ollama 0.35, Nimble 9B caught 81% of attacks and only 63% of instructions planted in ordinary emails, versus Jev's 89% and 92%, so the author is keeping Jev for now.
Can a local model replace a cloud Jev as a prompt-injection gate for my AI agent? I benchmarked the new decision models in Ollama 0.35 on 718 test items. Nimble 9B came closest: it caught 81% of attacks (Jev on Venice: 89%) and it's the best local model I've tested. But it blocks only 63% of instructions planted in ordinary emails, against Jev's 92%. I'm keeping Jev for now. If you want nothing to leave your machine, Nimble is now one config line in the hermes-firewall plugin (~11 GB RAM). https://juraj.bednar.io/en/blog-en/2026/09/28/a-prompt-injection-gate-for-my-ai-agent-what-worked-what-didnt-and-the-benchmark/#local-models